| program(1.0) |
| [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3520.4.1"}, {"coremlc-version", "3520.5.1"}, {"coremltools-component-torch", "2.11.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})] |
| { |
| func main<ios17>(tensor<fp32, [1, 32]> latent, tensor<fp32, [1, 1]> s, tensor<fp32, [1, 1]> t, tensor<fp32, [1, 1024]> transformer_out) { |
| tensor<fp32, [512]> flow_net_input_proj_bias = const()[name = tensor<string, []>("flow_net_input_proj_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))]; |
| tensor<fp32, [512, 32]> flow_net_input_proj_weight = const()[name = tensor<string, []>("flow_net_input_proj_weight"), val = tensor<fp32, [512, 32]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2176)))]; |
| tensor<fp32, [512]> flow_net_time_embed_0_mlp_0_bias = const()[name = tensor<string, []>("flow_net_time_embed_0_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(67776)))]; |
| tensor<fp32, [512, 256]> flow_net_time_embed_0_mlp_0_weight = const()[name = tensor<string, []>("flow_net_time_embed_0_mlp_0_weight"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(69888)))]; |
| tensor<fp32, [512]> flow_net_time_embed_0_mlp_2_bias = const()[name = tensor<string, []>("flow_net_time_embed_0_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(594240)))]; |
| tensor<fp32, [512, 512]> flow_net_time_embed_0_mlp_2_weight = const()[name = tensor<string, []>("flow_net_time_embed_0_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(596352)))]; |
| tensor<fp32, [512]> flow_net_time_embed_1_mlp_0_bias = const()[name = tensor<string, []>("flow_net_time_embed_1_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1644992)))]; |
| tensor<fp32, [512, 256]> flow_net_time_embed_1_mlp_0_weight = const()[name = tensor<string, []>("flow_net_time_embed_1_mlp_0_weight"), val = tensor<fp32, [512, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1647104)))]; |
| tensor<fp32, [512]> flow_net_time_embed_1_mlp_2_bias = const()[name = tensor<string, []>("flow_net_time_embed_1_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2171456)))]; |
| tensor<fp32, [512, 512]> flow_net_time_embed_1_mlp_2_weight = const()[name = tensor<string, []>("flow_net_time_embed_1_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(2173568)))]; |
| tensor<fp32, [512]> flow_net_cond_embed_bias = const()[name = tensor<string, []>("flow_net_cond_embed_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3222208)))]; |
| tensor<fp32, [512, 1024]> flow_net_cond_embed_weight = const()[name = tensor<string, []>("flow_net_cond_embed_weight"), val = tensor<fp32, [512, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3224320)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_0_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_0_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5321536)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_0_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_0_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5327744)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_0_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_0_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8473536)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_0_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_0_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8475648)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_0_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_0_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8477760)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_0_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_0_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8479872)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_0_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_0_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9528512)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_0_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_0_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9530624)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_1_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_1_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10579264)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_1_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_1_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10585472)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_1_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_1_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13731264)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_1_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_1_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13733376)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_1_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_1_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13735488)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_1_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_1_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13737600)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_1_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_1_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(14786240)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_1_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_1_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(14788352)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_2_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_2_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15836992)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_2_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_2_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15843200)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_2_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_2_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18988992)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_2_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_2_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18991104)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_2_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_2_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18993216)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_2_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_2_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18995328)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_2_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_2_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(20043968)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_2_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_2_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(20046080)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_3_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_3_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(21094720)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_3_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_3_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(21100928)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_3_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_3_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24246720)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_3_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_3_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24248832)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_3_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_3_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24250944)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_3_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_3_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24253056)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_3_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_3_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(25301696)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_3_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_3_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(25303808)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_4_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_4_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26352448)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_4_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_4_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26358656)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_4_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_4_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29504448)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_4_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_4_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29506560)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_4_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_4_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29508672)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_4_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_4_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29510784)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_4_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_4_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30559424)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_4_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_4_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30561536)))]; |
| tensor<fp32, [1536]> flow_net_res_blocks_5_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_res_blocks_5_adaLN_modulation_1_bias"), val = tensor<fp32, [1536]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(31610176)))]; |
| tensor<fp32, [1536, 512]> flow_net_res_blocks_5_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_res_blocks_5_adaLN_modulation_1_weight"), val = tensor<fp32, [1536, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(31616384)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_5_in_ln_bias = const()[name = tensor<string, []>("flow_net_res_blocks_5_in_ln_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34762176)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_5_in_ln_weight = const()[name = tensor<string, []>("flow_net_res_blocks_5_in_ln_weight"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34764288)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_5_mlp_0_bias = const()[name = tensor<string, []>("flow_net_res_blocks_5_mlp_0_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34766400)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_5_mlp_0_weight = const()[name = tensor<string, []>("flow_net_res_blocks_5_mlp_0_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34768512)))]; |
| tensor<fp32, [512]> flow_net_res_blocks_5_mlp_2_bias = const()[name = tensor<string, []>("flow_net_res_blocks_5_mlp_2_bias"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35817152)))]; |
| tensor<fp32, [512, 512]> flow_net_res_blocks_5_mlp_2_weight = const()[name = tensor<string, []>("flow_net_res_blocks_5_mlp_2_weight"), val = tensor<fp32, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35819264)))]; |
| tensor<fp32, [1024]> flow_net_final_layer_adaLN_modulation_1_bias = const()[name = tensor<string, []>("flow_net_final_layer_adaLN_modulation_1_bias"), val = tensor<fp32, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36867904)))]; |
| tensor<fp32, [1024, 512]> flow_net_final_layer_adaLN_modulation_1_weight = const()[name = tensor<string, []>("flow_net_final_layer_adaLN_modulation_1_weight"), val = tensor<fp32, [1024, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36872064)))]; |
| tensor<fp32, [32]> flow_net_final_layer_linear_bias = const()[name = tensor<string, []>("flow_net_final_layer_linear_bias"), val = tensor<fp32, [32]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(38969280)))]; |
| tensor<fp32, [32, 512]> flow_net_final_layer_linear_weight = const()[name = tensor<string, []>("flow_net_final_layer_linear_weight"), val = tensor<fp32, [32, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(38969472)))]; |
| tensor<int32, []> var_9 = const()[name = tensor<string, []>("op_9"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> x_5 = linear(bias = flow_net_input_proj_bias, weight = flow_net_input_proj_weight, x = latent)[name = tensor<string, []>("linear_0")]; |
| tensor<fp32, [128]> const_0 = const()[name = tensor<string, []>("const_0"), val = tensor<fp32, [128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39035072)))]; |
| tensor<fp32, [1, 128]> args_1 = mul(x = s, y = const_0)[name = tensor<string, []>("args_1")]; |
| tensor<fp32, [1, 128]> var_39 = cos(x = args_1)[name = tensor<string, []>("op_39")]; |
| tensor<fp32, [1, 128]> var_40 = sin(x = args_1)[name = tensor<string, []>("op_40")]; |
| tensor<bool, []> input_1_interleave_0 = const()[name = tensor<string, []>("input_1_interleave_0"), val = tensor<bool, []>(false)]; |
| tensor<fp32, [1, 256]> input_1 = concat(axis = var_9, interleave = input_1_interleave_0, values = (var_39, var_40))[name = tensor<string, []>("input_1")]; |
| tensor<fp32, [1, 512]> input_3 = linear(bias = flow_net_time_embed_0_mlp_0_bias, weight = flow_net_time_embed_0_mlp_0_weight, x = input_1)[name = tensor<string, []>("linear_1")]; |
| tensor<fp32, [1, 512]> input_5 = silu(x = input_3)[name = tensor<string, []>("input_5")]; |
| tensor<fp32, [1, 512]> x_1 = linear(bias = flow_net_time_embed_0_mlp_2_bias, weight = flow_net_time_embed_0_mlp_2_weight, x = input_5)[name = tensor<string, []>("linear_2")]; |
| tensor<int32, [1]> reduce_mean_0_axes_0 = const()[name = tensor<string, []>("reduce_mean_0_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_0_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_0_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_0 = reduce_mean(axes = reduce_mean_0_axes_0, keep_dims = reduce_mean_0_keep_dims_0, x = x_1)[name = tensor<string, []>("reduce_mean_0")]; |
| tensor<fp32, [1, 512]> sub_0 = sub(x = x_1, y = reduce_mean_0)[name = tensor<string, []>("sub_0")]; |
| tensor<fp32, [1, 512]> square_0 = square(x = sub_0)[name = tensor<string, []>("square_0")]; |
| tensor<int32, [1]> reduce_mean_1_axes_0 = const()[name = tensor<string, []>("reduce_mean_1_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_1_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_1_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_1 = reduce_mean(axes = reduce_mean_1_axes_0, keep_dims = reduce_mean_1_keep_dims_0, x = square_0)[name = tensor<string, []>("reduce_mean_1")]; |
| tensor<fp32, []> real_div_0 = const()[name = tensor<string, []>("real_div_0"), val = tensor<fp32, []>(0x1.00804p+0)]; |
| tensor<fp32, [1, 1]> mul_0 = mul(x = reduce_mean_1, y = real_div_0)[name = tensor<string, []>("mul_0")]; |
| tensor<fp32, []> var_56 = const()[name = tensor<string, []>("op_56"), val = tensor<fp32, []>(0x1.4f8b58p-17)]; |
| tensor<fp32, [1, 1]> var_1 = add(x = mul_0, y = var_56)[name = tensor<string, []>("var_1")]; |
| tensor<fp32, [512]> const_1 = const()[name = tensor<string, []>("const_1"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39035648)))]; |
| tensor<fp32, []> var_59_epsilon_0 = const()[name = tensor<string, []>("op_59_epsilon_0"), val = tensor<fp32, []>(0x1.197998p-40)]; |
| tensor<fp32, [1, 1]> var_59 = rsqrt(epsilon = var_59_epsilon_0, x = var_1)[name = tensor<string, []>("op_59")]; |
| tensor<fp32, [1, 512]> var_60 = mul(x = const_1, y = var_59)[name = tensor<string, []>("op_60")]; |
| tensor<fp32, [1, 512]> var_61 = mul(x = x_1, y = var_60)[name = tensor<string, []>("op_61")]; |
| tensor<fp32, [1, 128]> args = mul(x = t, y = const_0)[name = tensor<string, []>("args")]; |
| tensor<fp32, [1, 128]> var_69 = cos(x = args)[name = tensor<string, []>("op_69")]; |
| tensor<fp32, [1, 128]> var_70 = sin(x = args)[name = tensor<string, []>("op_70")]; |
| tensor<bool, []> input_7_interleave_0 = const()[name = tensor<string, []>("input_7_interleave_0"), val = tensor<bool, []>(false)]; |
| tensor<fp32, [1, 256]> input_7 = concat(axis = var_9, interleave = input_7_interleave_0, values = (var_69, var_70))[name = tensor<string, []>("input_7")]; |
| tensor<fp32, [1, 512]> input_9 = linear(bias = flow_net_time_embed_1_mlp_0_bias, weight = flow_net_time_embed_1_mlp_0_weight, x = input_7)[name = tensor<string, []>("linear_3")]; |
| tensor<fp32, [1, 512]> input_11 = silu(x = input_9)[name = tensor<string, []>("input_11")]; |
| tensor<fp32, [1, 512]> x_3 = linear(bias = flow_net_time_embed_1_mlp_2_bias, weight = flow_net_time_embed_1_mlp_2_weight, x = input_11)[name = tensor<string, []>("linear_4")]; |
| tensor<int32, [1]> reduce_mean_2_axes_0 = const()[name = tensor<string, []>("reduce_mean_2_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_2_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_2_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_2 = reduce_mean(axes = reduce_mean_2_axes_0, keep_dims = reduce_mean_2_keep_dims_0, x = x_3)[name = tensor<string, []>("reduce_mean_2")]; |
| tensor<fp32, [1, 512]> sub_2 = sub(x = x_3, y = reduce_mean_2)[name = tensor<string, []>("sub_2")]; |
| tensor<fp32, [1, 512]> square_1 = square(x = sub_2)[name = tensor<string, []>("square_1")]; |
| tensor<int32, [1]> reduce_mean_3_axes_0 = const()[name = tensor<string, []>("reduce_mean_3_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_3_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_3_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_3 = reduce_mean(axes = reduce_mean_3_axes_0, keep_dims = reduce_mean_3_keep_dims_0, x = square_1)[name = tensor<string, []>("reduce_mean_3")]; |
| tensor<fp32, []> real_div_1 = const()[name = tensor<string, []>("real_div_1"), val = tensor<fp32, []>(0x1.00804p+0)]; |
| tensor<fp32, [1, 1]> mul_1 = mul(x = reduce_mean_3, y = real_div_1)[name = tensor<string, []>("mul_1")]; |
| tensor<fp32, []> var_86 = const()[name = tensor<string, []>("op_86"), val = tensor<fp32, []>(0x1.4f8b58p-17)]; |
| tensor<fp32, [1, 1]> var_3 = add(x = mul_1, y = var_86)[name = tensor<string, []>("var_3")]; |
| tensor<fp32, [512]> const_3 = const()[name = tensor<string, []>("const_3"), val = tensor<fp32, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39037760)))]; |
| tensor<fp32, []> var_89_epsilon_0 = const()[name = tensor<string, []>("op_89_epsilon_0"), val = tensor<fp32, []>(0x1.197998p-40)]; |
| tensor<fp32, [1, 1]> var_89 = rsqrt(epsilon = var_89_epsilon_0, x = var_3)[name = tensor<string, []>("op_89")]; |
| tensor<fp32, [1, 512]> var_90 = mul(x = const_3, y = var_89)[name = tensor<string, []>("op_90")]; |
| tensor<fp32, [1, 512]> var_91 = mul(x = x_3, y = var_90)[name = tensor<string, []>("op_91")]; |
| tensor<fp32, [1, 512]> var_93 = add(x = var_61, y = var_91)[name = tensor<string, []>("op_93")]; |
| tensor<fp32, []> _inversed_t_combined_y_0 = const()[name = tensor<string, []>("_inversed_t_combined_y_0"), val = tensor<fp32, []>(0x1p-1)]; |
| tensor<fp32, [1, 512]> _inversed_t_combined = mul(x = var_93, y = _inversed_t_combined_y_0)[name = tensor<string, []>("_inversed_t_combined")]; |
| tensor<fp32, [1, 512]> c = linear(bias = flow_net_cond_embed_bias, weight = flow_net_cond_embed_weight, x = transformer_out)[name = tensor<string, []>("linear_5")]; |
| tensor<fp32, [1, 512]> input_13 = add(x = _inversed_t_combined, y = c)[name = tensor<string, []>("input_13")]; |
| tensor<fp32, [1, 512]> input_15 = silu(x = input_13)[name = tensor<string, []>("input_15")]; |
| tensor<fp32, [1, 1536]> var_107 = linear(bias = flow_net_res_blocks_0_adaLN_modulation_1_bias, weight = flow_net_res_blocks_0_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_6")]; |
| tensor<int32, [3]> var_108_split_sizes_0 = const()[name = tensor<string, []>("op_108_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_108_axis_0 = const()[name = tensor<string, []>("op_108_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_108_0, tensor<fp32, [1, 512]> var_108_1, tensor<fp32, [1, 512]> var_108_2 = split(axis = var_108_axis_0, split_sizes = var_108_split_sizes_0, x = var_107)[name = tensor<string, []>("op_108")]; |
| tensor<int32, [1]> mean_1_axes_0 = const()[name = tensor<string, []>("mean_1_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_1_keep_dims_0 = const()[name = tensor<string, []>("mean_1_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_1 = reduce_mean(axes = mean_1_axes_0, keep_dims = mean_1_keep_dims_0, x = x_5)[name = tensor<string, []>("mean_1")]; |
| tensor<fp32, [1, 512]> sub_4 = sub(x = x_5, y = mean_1)[name = tensor<string, []>("sub_4")]; |
| tensor<fp32, [1, 512]> square_2 = square(x = sub_4)[name = tensor<string, []>("square_2")]; |
| tensor<int32, [1]> reduce_mean_5_axes_0 = const()[name = tensor<string, []>("reduce_mean_5_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_5_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_5_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_5 = reduce_mean(axes = reduce_mean_5_axes_0, keep_dims = reduce_mean_5_keep_dims_0, x = square_2)[name = tensor<string, []>("reduce_mean_5")]; |
| tensor<fp32, []> var_118 = const()[name = tensor<string, []>("op_118"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_119 = add(x = reduce_mean_5, y = var_118)[name = tensor<string, []>("op_119")]; |
| tensor<fp32, [1, 1]> var_120 = sqrt(x = var_119)[name = tensor<string, []>("op_120")]; |
| tensor<fp32, [1, 512]> x_7 = real_div(x = sub_4, y = var_120)[name = tensor<string, []>("x_7")]; |
| tensor<fp32, [1, 512]> var_122 = mul(x = x_7, y = flow_net_res_blocks_0_in_ln_weight)[name = tensor<string, []>("op_122")]; |
| tensor<fp32, [1, 512]> x_9 = add(x = var_122, y = flow_net_res_blocks_0_in_ln_bias)[name = tensor<string, []>("x_9")]; |
| tensor<fp32, []> var_124_promoted = const()[name = tensor<string, []>("op_124_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_125 = add(x = var_108_1, y = var_124_promoted)[name = tensor<string, []>("op_125")]; |
| tensor<fp32, [1, 512]> var_126 = mul(x = x_9, y = var_125)[name = tensor<string, []>("op_126")]; |
| tensor<fp32, [1, 512]> input_17 = add(x = var_126, y = var_108_0)[name = tensor<string, []>("input_17")]; |
| tensor<fp32, [1, 512]> input_19 = linear(bias = flow_net_res_blocks_0_mlp_0_bias, weight = flow_net_res_blocks_0_mlp_0_weight, x = input_17)[name = tensor<string, []>("linear_7")]; |
| tensor<fp32, [1, 512]> input_21 = silu(x = input_19)[name = tensor<string, []>("input_21")]; |
| tensor<fp32, [1, 512]> h_1 = linear(bias = flow_net_res_blocks_0_mlp_2_bias, weight = flow_net_res_blocks_0_mlp_2_weight, x = input_21)[name = tensor<string, []>("linear_8")]; |
| tensor<fp32, [1, 512]> var_137 = mul(x = var_108_2, y = h_1)[name = tensor<string, []>("op_137")]; |
| tensor<fp32, [1, 512]> x_11 = add(x = x_5, y = var_137)[name = tensor<string, []>("x_11")]; |
| tensor<fp32, [1, 1536]> var_146 = linear(bias = flow_net_res_blocks_1_adaLN_modulation_1_bias, weight = flow_net_res_blocks_1_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_9")]; |
| tensor<int32, [3]> var_147_split_sizes_0 = const()[name = tensor<string, []>("op_147_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_147_axis_0 = const()[name = tensor<string, []>("op_147_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_147_0, tensor<fp32, [1, 512]> var_147_1, tensor<fp32, [1, 512]> var_147_2 = split(axis = var_147_axis_0, split_sizes = var_147_split_sizes_0, x = var_146)[name = tensor<string, []>("op_147")]; |
| tensor<int32, [1]> mean_3_axes_0 = const()[name = tensor<string, []>("mean_3_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_3_keep_dims_0 = const()[name = tensor<string, []>("mean_3_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_3 = reduce_mean(axes = mean_3_axes_0, keep_dims = mean_3_keep_dims_0, x = x_11)[name = tensor<string, []>("mean_3")]; |
| tensor<fp32, [1, 512]> sub_5 = sub(x = x_11, y = mean_3)[name = tensor<string, []>("sub_5")]; |
| tensor<fp32, [1, 512]> square_3 = square(x = sub_5)[name = tensor<string, []>("square_3")]; |
| tensor<int32, [1]> reduce_mean_7_axes_0 = const()[name = tensor<string, []>("reduce_mean_7_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_7_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_7_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_7 = reduce_mean(axes = reduce_mean_7_axes_0, keep_dims = reduce_mean_7_keep_dims_0, x = square_3)[name = tensor<string, []>("reduce_mean_7")]; |
| tensor<fp32, []> var_157 = const()[name = tensor<string, []>("op_157"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_158 = add(x = reduce_mean_7, y = var_157)[name = tensor<string, []>("op_158")]; |
| tensor<fp32, [1, 1]> var_159 = sqrt(x = var_158)[name = tensor<string, []>("op_159")]; |
| tensor<fp32, [1, 512]> x_13 = real_div(x = sub_5, y = var_159)[name = tensor<string, []>("x_13")]; |
| tensor<fp32, [1, 512]> var_161 = mul(x = x_13, y = flow_net_res_blocks_1_in_ln_weight)[name = tensor<string, []>("op_161")]; |
| tensor<fp32, [1, 512]> x_15 = add(x = var_161, y = flow_net_res_blocks_1_in_ln_bias)[name = tensor<string, []>("x_15")]; |
| tensor<fp32, []> var_163_promoted = const()[name = tensor<string, []>("op_163_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_164 = add(x = var_147_1, y = var_163_promoted)[name = tensor<string, []>("op_164")]; |
| tensor<fp32, [1, 512]> var_165 = mul(x = x_15, y = var_164)[name = tensor<string, []>("op_165")]; |
| tensor<fp32, [1, 512]> input_25 = add(x = var_165, y = var_147_0)[name = tensor<string, []>("input_25")]; |
| tensor<fp32, [1, 512]> input_27 = linear(bias = flow_net_res_blocks_1_mlp_0_bias, weight = flow_net_res_blocks_1_mlp_0_weight, x = input_25)[name = tensor<string, []>("linear_10")]; |
| tensor<fp32, [1, 512]> input_29 = silu(x = input_27)[name = tensor<string, []>("input_29")]; |
| tensor<fp32, [1, 512]> h_3 = linear(bias = flow_net_res_blocks_1_mlp_2_bias, weight = flow_net_res_blocks_1_mlp_2_weight, x = input_29)[name = tensor<string, []>("linear_11")]; |
| tensor<fp32, [1, 512]> var_176 = mul(x = var_147_2, y = h_3)[name = tensor<string, []>("op_176")]; |
| tensor<fp32, [1, 512]> x_17 = add(x = x_11, y = var_176)[name = tensor<string, []>("x_17")]; |
| tensor<fp32, [1, 1536]> var_185 = linear(bias = flow_net_res_blocks_2_adaLN_modulation_1_bias, weight = flow_net_res_blocks_2_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_12")]; |
| tensor<int32, [3]> var_186_split_sizes_0 = const()[name = tensor<string, []>("op_186_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_186_axis_0 = const()[name = tensor<string, []>("op_186_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_186_0, tensor<fp32, [1, 512]> var_186_1, tensor<fp32, [1, 512]> var_186_2 = split(axis = var_186_axis_0, split_sizes = var_186_split_sizes_0, x = var_185)[name = tensor<string, []>("op_186")]; |
| tensor<int32, [1]> mean_5_axes_0 = const()[name = tensor<string, []>("mean_5_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_5_keep_dims_0 = const()[name = tensor<string, []>("mean_5_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_5 = reduce_mean(axes = mean_5_axes_0, keep_dims = mean_5_keep_dims_0, x = x_17)[name = tensor<string, []>("mean_5")]; |
| tensor<fp32, [1, 512]> sub_6 = sub(x = x_17, y = mean_5)[name = tensor<string, []>("sub_6")]; |
| tensor<fp32, [1, 512]> square_4 = square(x = sub_6)[name = tensor<string, []>("square_4")]; |
| tensor<int32, [1]> reduce_mean_9_axes_0 = const()[name = tensor<string, []>("reduce_mean_9_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_9_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_9_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_9 = reduce_mean(axes = reduce_mean_9_axes_0, keep_dims = reduce_mean_9_keep_dims_0, x = square_4)[name = tensor<string, []>("reduce_mean_9")]; |
| tensor<fp32, []> var_196 = const()[name = tensor<string, []>("op_196"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_197 = add(x = reduce_mean_9, y = var_196)[name = tensor<string, []>("op_197")]; |
| tensor<fp32, [1, 1]> var_198 = sqrt(x = var_197)[name = tensor<string, []>("op_198")]; |
| tensor<fp32, [1, 512]> x_19 = real_div(x = sub_6, y = var_198)[name = tensor<string, []>("x_19")]; |
| tensor<fp32, [1, 512]> var_200 = mul(x = x_19, y = flow_net_res_blocks_2_in_ln_weight)[name = tensor<string, []>("op_200")]; |
| tensor<fp32, [1, 512]> x_21 = add(x = var_200, y = flow_net_res_blocks_2_in_ln_bias)[name = tensor<string, []>("x_21")]; |
| tensor<fp32, []> var_202_promoted = const()[name = tensor<string, []>("op_202_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_203 = add(x = var_186_1, y = var_202_promoted)[name = tensor<string, []>("op_203")]; |
| tensor<fp32, [1, 512]> var_204 = mul(x = x_21, y = var_203)[name = tensor<string, []>("op_204")]; |
| tensor<fp32, [1, 512]> input_33 = add(x = var_204, y = var_186_0)[name = tensor<string, []>("input_33")]; |
| tensor<fp32, [1, 512]> input_35 = linear(bias = flow_net_res_blocks_2_mlp_0_bias, weight = flow_net_res_blocks_2_mlp_0_weight, x = input_33)[name = tensor<string, []>("linear_13")]; |
| tensor<fp32, [1, 512]> input_37 = silu(x = input_35)[name = tensor<string, []>("input_37")]; |
| tensor<fp32, [1, 512]> h_5 = linear(bias = flow_net_res_blocks_2_mlp_2_bias, weight = flow_net_res_blocks_2_mlp_2_weight, x = input_37)[name = tensor<string, []>("linear_14")]; |
| tensor<fp32, [1, 512]> var_215 = mul(x = var_186_2, y = h_5)[name = tensor<string, []>("op_215")]; |
| tensor<fp32, [1, 512]> x_23 = add(x = x_17, y = var_215)[name = tensor<string, []>("x_23")]; |
| tensor<fp32, [1, 1536]> var_224 = linear(bias = flow_net_res_blocks_3_adaLN_modulation_1_bias, weight = flow_net_res_blocks_3_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_15")]; |
| tensor<int32, [3]> var_225_split_sizes_0 = const()[name = tensor<string, []>("op_225_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_225_axis_0 = const()[name = tensor<string, []>("op_225_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_225_0, tensor<fp32, [1, 512]> var_225_1, tensor<fp32, [1, 512]> var_225_2 = split(axis = var_225_axis_0, split_sizes = var_225_split_sizes_0, x = var_224)[name = tensor<string, []>("op_225")]; |
| tensor<int32, [1]> mean_7_axes_0 = const()[name = tensor<string, []>("mean_7_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_7_keep_dims_0 = const()[name = tensor<string, []>("mean_7_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_7 = reduce_mean(axes = mean_7_axes_0, keep_dims = mean_7_keep_dims_0, x = x_23)[name = tensor<string, []>("mean_7")]; |
| tensor<fp32, [1, 512]> sub_7 = sub(x = x_23, y = mean_7)[name = tensor<string, []>("sub_7")]; |
| tensor<fp32, [1, 512]> square_5 = square(x = sub_7)[name = tensor<string, []>("square_5")]; |
| tensor<int32, [1]> reduce_mean_11_axes_0 = const()[name = tensor<string, []>("reduce_mean_11_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_11_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_11_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_11 = reduce_mean(axes = reduce_mean_11_axes_0, keep_dims = reduce_mean_11_keep_dims_0, x = square_5)[name = tensor<string, []>("reduce_mean_11")]; |
| tensor<fp32, []> var_235 = const()[name = tensor<string, []>("op_235"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_236 = add(x = reduce_mean_11, y = var_235)[name = tensor<string, []>("op_236")]; |
| tensor<fp32, [1, 1]> var_237 = sqrt(x = var_236)[name = tensor<string, []>("op_237")]; |
| tensor<fp32, [1, 512]> x_25 = real_div(x = sub_7, y = var_237)[name = tensor<string, []>("x_25")]; |
| tensor<fp32, [1, 512]> var_239 = mul(x = x_25, y = flow_net_res_blocks_3_in_ln_weight)[name = tensor<string, []>("op_239")]; |
| tensor<fp32, [1, 512]> x_27 = add(x = var_239, y = flow_net_res_blocks_3_in_ln_bias)[name = tensor<string, []>("x_27")]; |
| tensor<fp32, []> var_241_promoted = const()[name = tensor<string, []>("op_241_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_242 = add(x = var_225_1, y = var_241_promoted)[name = tensor<string, []>("op_242")]; |
| tensor<fp32, [1, 512]> var_243 = mul(x = x_27, y = var_242)[name = tensor<string, []>("op_243")]; |
| tensor<fp32, [1, 512]> input_41 = add(x = var_243, y = var_225_0)[name = tensor<string, []>("input_41")]; |
| tensor<fp32, [1, 512]> input_43 = linear(bias = flow_net_res_blocks_3_mlp_0_bias, weight = flow_net_res_blocks_3_mlp_0_weight, x = input_41)[name = tensor<string, []>("linear_16")]; |
| tensor<fp32, [1, 512]> input_45 = silu(x = input_43)[name = tensor<string, []>("input_45")]; |
| tensor<fp32, [1, 512]> h_7 = linear(bias = flow_net_res_blocks_3_mlp_2_bias, weight = flow_net_res_blocks_3_mlp_2_weight, x = input_45)[name = tensor<string, []>("linear_17")]; |
| tensor<fp32, [1, 512]> var_254 = mul(x = var_225_2, y = h_7)[name = tensor<string, []>("op_254")]; |
| tensor<fp32, [1, 512]> x_29 = add(x = x_23, y = var_254)[name = tensor<string, []>("x_29")]; |
| tensor<fp32, [1, 1536]> var_263 = linear(bias = flow_net_res_blocks_4_adaLN_modulation_1_bias, weight = flow_net_res_blocks_4_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_18")]; |
| tensor<int32, [3]> var_264_split_sizes_0 = const()[name = tensor<string, []>("op_264_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_264_axis_0 = const()[name = tensor<string, []>("op_264_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_264_0, tensor<fp32, [1, 512]> var_264_1, tensor<fp32, [1, 512]> var_264_2 = split(axis = var_264_axis_0, split_sizes = var_264_split_sizes_0, x = var_263)[name = tensor<string, []>("op_264")]; |
| tensor<int32, [1]> mean_9_axes_0 = const()[name = tensor<string, []>("mean_9_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_9_keep_dims_0 = const()[name = tensor<string, []>("mean_9_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_9 = reduce_mean(axes = mean_9_axes_0, keep_dims = mean_9_keep_dims_0, x = x_29)[name = tensor<string, []>("mean_9")]; |
| tensor<fp32, [1, 512]> sub_8 = sub(x = x_29, y = mean_9)[name = tensor<string, []>("sub_8")]; |
| tensor<fp32, [1, 512]> square_6 = square(x = sub_8)[name = tensor<string, []>("square_6")]; |
| tensor<int32, [1]> reduce_mean_13_axes_0 = const()[name = tensor<string, []>("reduce_mean_13_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_13_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_13_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_13 = reduce_mean(axes = reduce_mean_13_axes_0, keep_dims = reduce_mean_13_keep_dims_0, x = square_6)[name = tensor<string, []>("reduce_mean_13")]; |
| tensor<fp32, []> var_274 = const()[name = tensor<string, []>("op_274"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_275 = add(x = reduce_mean_13, y = var_274)[name = tensor<string, []>("op_275")]; |
| tensor<fp32, [1, 1]> var_276 = sqrt(x = var_275)[name = tensor<string, []>("op_276")]; |
| tensor<fp32, [1, 512]> x_31 = real_div(x = sub_8, y = var_276)[name = tensor<string, []>("x_31")]; |
| tensor<fp32, [1, 512]> var_278 = mul(x = x_31, y = flow_net_res_blocks_4_in_ln_weight)[name = tensor<string, []>("op_278")]; |
| tensor<fp32, [1, 512]> x_33 = add(x = var_278, y = flow_net_res_blocks_4_in_ln_bias)[name = tensor<string, []>("x_33")]; |
| tensor<fp32, []> var_280_promoted = const()[name = tensor<string, []>("op_280_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_281 = add(x = var_264_1, y = var_280_promoted)[name = tensor<string, []>("op_281")]; |
| tensor<fp32, [1, 512]> var_282 = mul(x = x_33, y = var_281)[name = tensor<string, []>("op_282")]; |
| tensor<fp32, [1, 512]> input_49 = add(x = var_282, y = var_264_0)[name = tensor<string, []>("input_49")]; |
| tensor<fp32, [1, 512]> input_51 = linear(bias = flow_net_res_blocks_4_mlp_0_bias, weight = flow_net_res_blocks_4_mlp_0_weight, x = input_49)[name = tensor<string, []>("linear_19")]; |
| tensor<fp32, [1, 512]> input_53 = silu(x = input_51)[name = tensor<string, []>("input_53")]; |
| tensor<fp32, [1, 512]> h_9 = linear(bias = flow_net_res_blocks_4_mlp_2_bias, weight = flow_net_res_blocks_4_mlp_2_weight, x = input_53)[name = tensor<string, []>("linear_20")]; |
| tensor<fp32, [1, 512]> var_293 = mul(x = var_264_2, y = h_9)[name = tensor<string, []>("op_293")]; |
| tensor<fp32, [1, 512]> x_35 = add(x = x_29, y = var_293)[name = tensor<string, []>("x_35")]; |
| tensor<fp32, [1, 1536]> var_302 = linear(bias = flow_net_res_blocks_5_adaLN_modulation_1_bias, weight = flow_net_res_blocks_5_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_21")]; |
| tensor<int32, [3]> var_303_split_sizes_0 = const()[name = tensor<string, []>("op_303_split_sizes_0"), val = tensor<int32, [3]>([512, 512, 512])]; |
| tensor<int32, []> var_303_axis_0 = const()[name = tensor<string, []>("op_303_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_303_0, tensor<fp32, [1, 512]> var_303_1, tensor<fp32, [1, 512]> var_303_2 = split(axis = var_303_axis_0, split_sizes = var_303_split_sizes_0, x = var_302)[name = tensor<string, []>("op_303")]; |
| tensor<int32, [1]> mean_11_axes_0 = const()[name = tensor<string, []>("mean_11_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_11_keep_dims_0 = const()[name = tensor<string, []>("mean_11_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean_11 = reduce_mean(axes = mean_11_axes_0, keep_dims = mean_11_keep_dims_0, x = x_35)[name = tensor<string, []>("mean_11")]; |
| tensor<fp32, [1, 512]> sub_9 = sub(x = x_35, y = mean_11)[name = tensor<string, []>("sub_9")]; |
| tensor<fp32, [1, 512]> square_7 = square(x = sub_9)[name = tensor<string, []>("square_7")]; |
| tensor<int32, [1]> reduce_mean_15_axes_0 = const()[name = tensor<string, []>("reduce_mean_15_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_15_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_15_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_15 = reduce_mean(axes = reduce_mean_15_axes_0, keep_dims = reduce_mean_15_keep_dims_0, x = square_7)[name = tensor<string, []>("reduce_mean_15")]; |
| tensor<fp32, []> var_313 = const()[name = tensor<string, []>("op_313"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_314 = add(x = reduce_mean_15, y = var_313)[name = tensor<string, []>("op_314")]; |
| tensor<fp32, [1, 1]> var_315 = sqrt(x = var_314)[name = tensor<string, []>("op_315")]; |
| tensor<fp32, [1, 512]> x_37 = real_div(x = sub_9, y = var_315)[name = tensor<string, []>("x_37")]; |
| tensor<fp32, [1, 512]> var_317 = mul(x = x_37, y = flow_net_res_blocks_5_in_ln_weight)[name = tensor<string, []>("op_317")]; |
| tensor<fp32, [1, 512]> x_39 = add(x = var_317, y = flow_net_res_blocks_5_in_ln_bias)[name = tensor<string, []>("x_39")]; |
| tensor<fp32, []> var_319_promoted = const()[name = tensor<string, []>("op_319_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_320 = add(x = var_303_1, y = var_319_promoted)[name = tensor<string, []>("op_320")]; |
| tensor<fp32, [1, 512]> var_321 = mul(x = x_39, y = var_320)[name = tensor<string, []>("op_321")]; |
| tensor<fp32, [1, 512]> input_57 = add(x = var_321, y = var_303_0)[name = tensor<string, []>("input_57")]; |
| tensor<fp32, [1, 512]> input_59 = linear(bias = flow_net_res_blocks_5_mlp_0_bias, weight = flow_net_res_blocks_5_mlp_0_weight, x = input_57)[name = tensor<string, []>("linear_22")]; |
| tensor<fp32, [1, 512]> input_61 = silu(x = input_59)[name = tensor<string, []>("input_61")]; |
| tensor<fp32, [1, 512]> h = linear(bias = flow_net_res_blocks_5_mlp_2_bias, weight = flow_net_res_blocks_5_mlp_2_weight, x = input_61)[name = tensor<string, []>("linear_23")]; |
| tensor<fp32, [1, 512]> var_332 = mul(x = var_303_2, y = h)[name = tensor<string, []>("op_332")]; |
| tensor<fp32, [1, 512]> x_41 = add(x = x_35, y = var_332)[name = tensor<string, []>("x_41")]; |
| tensor<fp32, [1, 1024]> var_340 = linear(bias = flow_net_final_layer_adaLN_modulation_1_bias, weight = flow_net_final_layer_adaLN_modulation_1_weight, x = input_15)[name = tensor<string, []>("linear_24")]; |
| tensor<int32, [2]> var_341_split_sizes_0 = const()[name = tensor<string, []>("op_341_split_sizes_0"), val = tensor<int32, [2]>([512, 512])]; |
| tensor<int32, []> var_341_axis_0 = const()[name = tensor<string, []>("op_341_axis_0"), val = tensor<int32, []>(-1)]; |
| tensor<fp32, [1, 512]> var_341_0, tensor<fp32, [1, 512]> var_341_1 = split(axis = var_341_axis_0, split_sizes = var_341_split_sizes_0, x = var_340)[name = tensor<string, []>("op_341")]; |
| tensor<int32, [1]> mean_axes_0 = const()[name = tensor<string, []>("mean_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> mean_keep_dims_0 = const()[name = tensor<string, []>("mean_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> mean = reduce_mean(axes = mean_axes_0, keep_dims = mean_keep_dims_0, x = x_41)[name = tensor<string, []>("mean")]; |
| tensor<fp32, [1, 512]> sub_10 = sub(x = x_41, y = mean)[name = tensor<string, []>("sub_10")]; |
| tensor<fp32, [1, 512]> square_8 = square(x = sub_10)[name = tensor<string, []>("square_8")]; |
| tensor<int32, [1]> reduce_mean_17_axes_0 = const()[name = tensor<string, []>("reduce_mean_17_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<bool, []> reduce_mean_17_keep_dims_0 = const()[name = tensor<string, []>("reduce_mean_17_keep_dims_0"), val = tensor<bool, []>(true)]; |
| tensor<fp32, [1, 1]> reduce_mean_17 = reduce_mean(axes = reduce_mean_17_axes_0, keep_dims = reduce_mean_17_keep_dims_0, x = square_8)[name = tensor<string, []>("reduce_mean_17")]; |
| tensor<fp32, []> var_348 = const()[name = tensor<string, []>("op_348"), val = tensor<fp32, []>(0x1.0c6f7ap-20)]; |
| tensor<fp32, [1, 1]> var_349 = add(x = reduce_mean_17, y = var_348)[name = tensor<string, []>("op_349")]; |
| tensor<fp32, [1, 1]> var_350 = sqrt(x = var_349)[name = tensor<string, []>("op_350")]; |
| tensor<fp32, [1, 512]> x = real_div(x = sub_10, y = var_350)[name = tensor<string, []>("x")]; |
| tensor<fp32, []> var_352_promoted = const()[name = tensor<string, []>("op_352_promoted"), val = tensor<fp32, []>(0x1p+0)]; |
| tensor<fp32, [1, 512]> var_353 = add(x = var_341_1, y = var_352_promoted)[name = tensor<string, []>("op_353")]; |
| tensor<fp32, [1, 512]> var_354 = mul(x = x, y = var_353)[name = tensor<string, []>("op_354")]; |
| tensor<fp32, [1, 512]> input = add(x = var_354, y = var_341_0)[name = tensor<string, []>("input")]; |
| tensor<fp32, [1, 32]> var_358 = linear(bias = flow_net_final_layer_linear_bias, weight = flow_net_final_layer_linear_weight, x = input)[name = tensor<string, []>("linear_25")]; |
| } -> (var_358); |
| } |
